Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to a specific individual named Moore in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    userDao
    -0.85
    ing
    -0.81
     كومونز
    -0.76
    ivel
    -0.75
    ة
    -0.75
     ddelweddau
    -0.74
    ';
    -0.72
     stří
    -0.69
    TEntity
    -0.69
    ByPrimaryKey
    -0.68
    POSITIVE LOGITS
     Moore
    1.52
    Moore
    1.40
     MOORE
    1.38
     moore
    1.30
    bellar
    0.91
     Moor
    0.91
     Moo
    0.84
    Moo
    0.84
    Moor
    0.82
    blower
    0.81
    Act Density 0.013%

    No Known Activations